Sign Up

Claude Opus 4.7

Anthropic
Announcement
Claude Opus 4.7 launch post cover

Cost/1M tokens

input
$5.00
cached
$0.50
output
$25.00
cache write
$6.25
Context
1Mtokens
Released
7mo ago

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.

How it ranks

Against its predecessor, similarly priced models and the models ranked around it.

DeepSWE 1.1

Best pass@1 per model · Higher is better

Not evaluated in DeepSWE 1.1

Arena Text

Best Arena rating per model · Higher is better

Arena #8

  1. 1511
    Muse WonderSimilar price
  2. 1503
    Claude Opus 4.6Predecessor
  3. 1503
    Claude Fable 5.1Nearby rank
  4. 1501
    Claude Opus 4.7
  5. 1497
    Gemini 3.8 FlashNearby rank
  6. 1496
    Muse Spark 1.3Nearby rank
  7. 1485
    GPT-5.6 SolSimilar price
  8. 1481
    GPT-5.5Similar price
  9. 1346
    GPT-4o (2024-05-13)Similar price

Level with Claude Opus 4.6 (predecessor, overlapping 95% CIs) · Ahead of 3 of 4 similarly priced models

Arena WebDev

Best Arena rating per model · Higher is better

Arena #48

  1. 1649
    Muse WonderSimilar price
  2. 1615
    GPT-5.6 SolSimilar price
  3. 1573
    Step 5 PreviewNearby rank
  4. 1564
    Mistral Large 4Nearby rank
  5. 1557
    Claude Opus 4.7
  6. 1555
    Claude Opus 4.8Nearby rank
  7. 1552
    Grok 4.5Nearby rank
  8. 1547
    Claude Opus 4.6Predecessor
  9. 1512
    GPT-5.5Similar price
  10. 1462
    GPT-5.4Similar price

Level with Claude Opus 4.6 (predecessor, overlapping 95% CIs) · Ahead of 2 of 4 similarly priced models

Arena Vision

Best Arena rating per model · Higher is better

Arena #2

  1. 1309
    Claude Fable 5Nearby rank
  2. 1300
    Claude Opus 4.7
  3. 1299
    Qwen3.8 MaxNearby rank
  4. 1299
    Claude Opus 4.6Predecessor
  5. 1288
    GPT-5.6 SolSimilar price
  6. 1285
    GPT-5.5Similar price
  7. 1282
    GPT-5.4Similar price
  8. 1162
    GPT-4o (2024-05-13)Similar price

Level with Claude Opus 4.6 (predecessor, overlapping 95% CIs) · Ahead of 3 of 4 similarly priced models

Arena Search

Best Arena rating per model · Higher is better

Arena #13

  1. 1255
    GPT-5.6 SolSimilar price
  2. 1245
    GPT-6 AstraSimilar price
  3. 1213
    Claude Opus 5Similar price
  4. 1213
    Claude Opus 5.5Nearby rank
  5. 1211
    GPT-6 LunaNearby rank
  6. 1210
    Claude Opus 4.7
  7. 1205
    Grok 4.5Nearby rank
  8. 1201
    Gemini 3 Pro PreviewNearby rank
  9. 1142
    Sonar ProSimilar price

Ahead of 1 of 4 similarly priced models

Arena Document

Best Arena rating per model · Higher is better

Arena #5

  1. 1498
    Claude Fable 5.1Nearby rank
  2. 1497
    Claude Opus 4.6Predecessor
  3. 1494
    Claude Opus 4.7
  4. 1486
    GPT-5.6 SolSimilar price
  5. 1486
    Claude Opus 5Nearby rank
  6. 1481
    GPT-5.5Similar price
  7. 1474
    GPT-6 AstraSimilar price
  8. 1471
    GPT-5.4Similar price

Level with Claude Opus 4.6 (predecessor, overlapping 95% CIs) · Ahead of 3 of 4 similarly priced models

Agent Arena

Best IPS score per model · Higher is better

Not ranked on Agent Arena yet

ARC-AGI-2

Best score per model · Higher is better

#22 of 85

  1. 95.0%
    GPT-6 AstraSimilar price
  2. 92.5%
    GPT-5.6 SolSimilar price
  3. 85.0%
    GPT-5.5Similar price
  4. 78.1%
    DeepSeek V4.1 Flash 1017Nearby rank
  5. 77.1%
    Gemini 3.1 Pro PreviewNearby rank
  6. 75.8%
    Claude Opus 4.7
  7. 74.0%
    GPT-5.4Similar price
  8. 72.9%
    DeepSeek V4.1 FlashNearby rank
  9. 64.6%
    Claude Opus 4.6Predecessor

+11.2 pts vs Claude Opus 4.6 (predecessor) · Ahead of 1 of 4 similarly priced models

FrontierMath-2025-02-28-Private

Best score per model · Higher is better

#4 of 58

  1. 47.6%
    GPT-5.4Similar price
  2. 47.2%
    Claude Opus 4.8Similar price
  3. 43.8%
    Claude Opus 4.7
  4. 40.7%
    Claude Opus 4.6Predecessor
  5. 40.7%
    GPT-5.2Nearby rank
  6. 32.4%
    Claude Sonnet 4.6Similar price
  7. 20.7%
    Claude Opus 4.5Similar price

+3.1 pts vs Claude Opus 4.6 (predecessor) · Ahead of 2 of 4 similarly priced models

FrontierMath-Tier-4-2025-07-01-Private

Best score per model · Higher is better

#3 of 46

  1. 31.3%
    Claude Opus 4.8Similar price
  2. 27.1%
    GPT-5.4Similar price
  3. 22.9%
    Claude Opus 4.7
  4. 22.9%
    Claude Opus 4.6Predecessor
  5. 18.8%
    GPT-5.2Nearby rank
  6. 8.3%
    Claude Sonnet 4.6Similar price
  7. 4.2%
    Claude Opus 4.5Similar price

Level with Claude Opus 4.6 (predecessor) · Ahead of 2 of 4 similarly priced models

FrontierMath-Tier-4-v2-Private

Best score per model · Higher is better

#32 of 72

  1. 97.6%
    GPT-6 AstraSimilar price
  2. 82.9%
    GPT-5.6 SolSimilar price
  3. 72.5%
    GPT-5.5Similar price
  4. 49.0%
    GPT-5.4Similar price
  5. 34.1%
    Qwen3.7 MaxNearby rank
  6. 34.1%
    Qwen3.8 Max (0902)Nearby rank
  7. 31.7%
    Claude Opus 4.7
  8. 31.7%
    Grok 4.6Nearby rank
  9. 31.7%
    GPT-5.2Nearby rank
  10. 26.8%
    Claude Opus 4.6Predecessor

+4.9 pts vs Claude Opus 4.6 (predecessor) · Ahead of 0 of 4 similarly priced models

FrontierMath-Tiers-1-3-v2-Private

Best score per model · Higher is better

#29 of 87

  1. 93.7%
    GPT-6 AstraSimilar price
  2. 89.1%
    GPT-5.6 SolSimilar price
  3. 85.3%
    GPT-5.5Similar price
  4. 78.6%
    GPT-5.4Similar price
  5. 71.6%
    Gemini 3.7 FlashNearby rank
  6. 71.2%
    DeepSeek V4.1 Flash 1017Nearby rank
  7. 70.2%
    Claude Opus 4.7
  8. 68.8%
    GLM 5.3Nearby rank
  9. 68.4%
    Gemini 3.8 FlashNearby rank
  10. 66.0%
    Claude Opus 4.6Predecessor

+4.2 pts vs Claude Opus 4.6 (predecessor) · Ahead of 0 of 4 similarly priced models

GPQA diamond

Best score per model · Higher is better

#43 of 161

  1. 93.5%
    GPT-5.6 SolSimilar price
  2. 93.3%
    GPT-5.4Similar price
  3. 90.7%
    GPT-5.5Similar price
  4. 90.5%
    Claude Opus 4.6Predecessor
  5. 90.5%
    Claude Sonnet 5Nearby rank
  6. 90.5%
    GPT-6 LunaNearby rank
  7. 90.2%
    Claude Opus 4.7
  8. 90.2%
    GLM 5.3 FlashNearby rank
  9. 89.9%
    GLM 5.1Nearby rank
  10. 48.9%
    GPT-4o (2024-05-13)Similar price

-0.4 pts vs Claude Opus 4.6 (predecessor) · Ahead of 1 of 4 similarly priced models

Humanity's Last Exam

Best score per model · Higher is better

#9 of 34

  1. 54.8%
    GPT-6 AstraSimilar price
  2. 37.5%
    Gemini 3 Pro PreviewNearby rank
  3. 36.2%
    GPT-5.4Similar price
  4. 36.2%
    Claude Opus 4.7
  5. 34.4%
    Claude Opus 4.6Predecessor
  6. 31.6%
    GPT-5 ProNearby rank
  7. 14.2%
    Claude Opus 4.5Similar price
  8. 7.5%
    Claude Sonnet 4.5Similar price

+1.8 pts vs Claude Opus 4.6 (predecessor) · Ahead of 2 of 4 similarly priced models

OSWorld 2.0

Best score per model · Higher is better

#4 of 9

  1. 31.4%
    Claude Opus 5Similar price
  2. 27.3%
    GPT-5.6 SolSimilar price
  3. 18.5%
    Claude Opus 4.8Similar price
  4. 13.9%
    Claude Opus 4.7
  5. 13.0%
    GPT-5.5Similar price
  6. 9.3%
    Claude Sonnet 4.6Earlier version

+4.6 pts vs Claude Sonnet 4.6 (earlier version) · Ahead of 1 of 4 similarly priced models

OTIS Mock AIME 2024-2025

Best score per model · Higher is better

#29 of 158

  1. 100.0%
    GPT-5.6 SolSimilar price
  2. 98.3%
    GPT-5.6 LunaNearby rank
  3. 98.1%
    Grok 4.7Nearby rank
  4. 97.8%
    Claude Opus 4.7
  5. 97.8%
    GPT-5.4Similar price
  6. 97.8%
    Grok 4.5Nearby rank
  7. 94.4%
    Claude Opus 4.6Predecessor
  8. 84.4%
    GPT-5.5Similar price
  9. 6.3%
    GPT-4o (2024-05-13)Similar price

+3.4 pts vs Claude Opus 4.6 (predecessor) · Ahead of 2 of 4 similarly priced models

SimpleQA Verified

Best score per model · Higher is better

#28 of 87

  1. 75.6%
    GPT-6 AstraSimilar price
  2. 69.7%
    GPT-5.6 SolSimilar price
  3. 63.0%
    GPT-5.5Similar price
  4. 52.9%
    DeepSeek V4 Pro 0813Nearby rank
  5. 52.0%
    Qwen3.6 Max PreviewNearby rank
  6. 51.7%
    Claude Opus 4.7
  7. 50.6%
    Kimi K3Nearby rank
  8. 50.1%
    GPT-5Nearby rank
  9. 47.0%
    Claude Opus 4.6Predecessor
  10. 45.1%
    GPT-5.4Similar price

+4.7 pts vs Claude Opus 4.6 (predecessor) · Ahead of 1 of 4 similarly priced models

SWE-bench Verified

Best score per model · Higher is better

#1 of 35

  1. 83.5%
    Claude Opus 4.7
  2. 79.3%
    Gemini 3.5 FlashNearby rank
  3. 78.7%
    GLM 5.2Nearby rank
  4. 76.9%
    GPT-5.4Similar price
  5. 76.7%
    Claude Opus 4.5Similar price
  6. 75.6%
    Claude Opus 4.6Predecessor
  7. 75.2%
    Claude Sonnet 4.6Similar price
  8. 71.3%
    Claude Sonnet 4.5Similar price

+7.9 pts vs Claude Opus 4.6 (predecessor) · Ahead of 4 of 4 similarly priced models

Terminal Bench

Best score per model · Higher is better

#3 of 49

  1. 84.7%
    GPT-5.5Similar price
  2. 81.8%
    GPT-5.4Similar price
  3. 80.2%
    Claude Opus 4.7
  4. 80.2%
    Gemini 3.1 Pro PreviewNearby rank
  5. 79.8%
    Claude Opus 4.6Predecessor
  6. 63.1%
    Claude Opus 4.5Similar price
  7. 53.4%
    Claude Sonnet 4.6Similar price

+0.4 pts vs Claude Opus 4.6 (predecessor) · Ahead of 2 of 4 similarly priced models

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Reasoning effort

ARC-AGI-2

Score by reasoning effort · Higher is better

GPQA diamond

Score by reasoning effort · Higher is better

OTIS Mock AIME 2024-2025

Score by reasoning effort · Higher is better

All published scores

  • Arena TextArena #81501

    Level with Claude Opus 4.6 (predecessor, overlapping 95% CIs)

    • high150195% CI 1497 to 1505 · 64,308 votes
    • default149495% CI 1490 to 1498 · 65,369 votes
    Source:Arena Text leaderboard, 2026-11-09
  • Arena WebDevArena #481557

    Level with Claude Opus 4.6 (predecessor, overlapping 95% CIs)

    • high155795% CI 1551 to 1563 · 17,604 votes
    • default155595% CI 1550 to 1561 · 17,929 votes
    Source:Arena WebDev leaderboard, 2026-11-10
  • Arena VisionArena #21300

    Level with Claude Opus 4.6 (predecessor, overlapping 95% CIs)

    • high129895% CI 1292 to 1305 · 22,609 votes
    • default130095% CI 1294 to 1307 · 23,777 votes
    Source:Arena Vision leaderboard, 2026-11-09
  • Arena SearchArena #131210
    • default121095% CI 1205 to 1215 · 121,890 votes
    Source:Arena Search leaderboard, 2026-11-09
  • Arena DocumentArena #51494

    Level with Claude Opus 4.6 (predecessor, overlapping 95% CIs)

    • high149495% CI 1488 to 1501 · 23,327 votes
    • default149495% CI 1488 to 1501 · 23,628 votes
    Source:Arena Document leaderboard, 2026-11-09
  • ARC-AGI-2#22 of 8575.8%

    +11.2 pts vs Claude Opus 4.6 (predecessor)

    • low62.1%
    • medium67.5%
    • high68.3%
    • max75.8%
    Source:External evaluation via Epoch AIOriginal-source terms apply
  • FrontierMath-2025-02-28-Private#4 of 5843.8%

    +3.1 pts vs Claude Opus 4.6 (predecessor)

    • xhigh43.8%
    Source:Epoch AI evaluation
  • FrontierMath-Tier-4-2025-07-01-Private#3 of 4622.9%

    Level with Claude Opus 4.6 (predecessor)

    • xhigh22.9%
    Source:Epoch AI evaluation
  • FrontierMath-Tier-4-v2-Private#32 of 7231.7%

    +4.9 pts vs Claude Opus 4.6 (predecessor)

    • max31.7%
    Source:Epoch AI evaluation
  • FrontierMath-Tiers-1-3-v2-Private#29 of 8770.2%

    +4.2 pts vs Claude Opus 4.6 (predecessor)

    • max70.2%
    Source:Epoch AI evaluation
  • GPQA diamond#43 of 16190.2%

    -0.4 pts vs Claude Opus 4.6 (predecessor)

    • xhigh90.2%
    • max86.4%
    Source:Epoch AI evaluation
  • Humanity's Last Exam#9 of 3436.2%

    +1.8 pts vs Claude Opus 4.6 (predecessor)

    • unknown36.2%
    Source:External evaluation via Epoch AIOriginal-source terms apply
  • OSWorld 2.0#4 of 913.9%

    +4.6 pts vs Claude Sonnet 4.6 (earlier version)

    • max13.9%
    Source:https://osworld-v2.xlang.ai/Original-source terms apply
  • OTIS Mock AIME 2024-2025#29 of 15897.8%

    +3.4 pts vs Claude Opus 4.6 (predecessor)

    • xhigh97.8%
    • max86.7%
    Source:Epoch AI evaluation
  • SimpleQA Verified#28 of 8751.7%

    +4.7 pts vs Claude Opus 4.6 (predecessor)

    • xhigh51.7%
    Source:Epoch AI evaluation
  • SWE-bench Verified#1 of 3583.5%

    +7.9 pts vs Claude Opus 4.6 (predecessor)

    • max83.5%
    Source:Epoch AI evaluation
  • Terminal Bench#3 of 4980.2%

    +0.4 pts vs Claude Opus 4.6 (predecessor)

    • unknown80.2%WOZCODE
    Source:https://www.tbench.ai/leaderboard/terminal-bench/2.0Original-source terms apply

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.